convex-realtime
Patterns for building reactive apps including subscription management, optimistic updates, cache behavior, and paginated queries with cursor-based loading
62
53%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/convex-realtime/SKILL.mdQuality
Discovery
42%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description effectively lists specific technical capabilities for reactive application patterns, demonstrating good specificity. However, it critically lacks any 'Use when...' guidance, making it difficult for Claude to know when to select this skill over others. The technical jargon may not match how users naturally phrase requests.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when building real-time features, implementing live data subscriptions, or handling infinite scroll/pagination'
Include more natural user-facing terms alongside technical ones, such as 'real-time updates', 'live data', 'infinite scroll', 'load more'
Specify the technology context (e.g., React Query, Apollo, specific frameworks) to reduce conflict with other frontend/backend skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'subscription management, optimistic updates, cache behavior, and paginated queries with cursor-based loading' - these are distinct, technical capabilities. | 3 / 3 |
Completeness | Describes WHAT (patterns for reactive apps with specific features) but completely lacks a 'Use when...' clause or any explicit trigger guidance for WHEN Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains relevant technical terms like 'reactive apps', 'subscription', 'optimistic updates', 'cache', 'paginated queries', 'cursor-based loading', but these are developer jargon rather than natural phrases users would say. Missing common variations like 'real-time', 'live updates', 'infinite scroll'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Reactive apps' is somewhat specific but could overlap with general frontend skills, state management skills, or API skills. The specific features help distinguish it, but without explicit triggers, conflict risk remains. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent executable code examples covering real-time subscriptions, optimistic updates, and pagination patterns. The main weaknesses are verbosity (could be more concise by removing explanatory content Claude already knows) and lack of explicit error handling workflows for operations that can fail. The content would benefit from being split into a concise overview with links to detailed pattern files.
Suggestions
Remove or significantly condense the 'How Convex Realtime Works' section - Claude understands these concepts
Add explicit error handling workflows for optimistic updates, showing what to do when mutations fail
Split detailed patterns (pagination, optimistic updates, chat example) into separate reference files, keeping SKILL.md as a concise overview with links
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some unnecessary explanatory sections like 'How Convex Realtime Works' that explain concepts Claude likely knows. The 'Best Practices' and 'Common Pitfalls' sections add value but could be more tightly integrated. | 2 / 3 |
Actionability | Excellent executable code examples throughout - all TypeScript/React code is complete, copy-paste ready, and includes both backend (Convex functions) and frontend (React components) implementations. Examples cover real-world patterns like chat apps and infinite scroll. | 3 / 3 |
Workflow Clarity | The skill presents patterns clearly but lacks explicit validation checkpoints. For operations like optimistic updates that can fail, there's no explicit error handling workflow or feedback loop for recovery beyond mentioning 'auto-rollback on error'. | 2 / 3 |
Progressive Disclosure | The skill has good section organization but is quite long (~350 lines) with extensive inline code that could be split into separate reference files. The References section at the end is helpful, but the main content could benefit from a shorter overview with links to detailed pattern files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
- Repository
- waynesutton/convexskills
- Commit
8ef49c9
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.